R Notebook

library(tidyverse)

Registered S3 methods overwritten by 'dbplyr':
  method         from
  print.tbl_lazy     
  print.tbl_sql      
── Attaching packages ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────── tidyverse 1.3.1 ──
✔ ggplot2 3.3.6     ✔ purrr   0.3.4
✔ tibble  3.1.7     ✔ dplyr   1.0.9
✔ tidyr   1.2.0     ✔ stringr 1.4.0
✔ readr   2.1.2     ✔ forcats 0.5.1
── Conflicts ─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()

international <- read_csv("clean_data/international.csv")

Warning: One or more parsing issues, see `problems()` for details

Rows: 32049 Columns: 9
── Column specification ─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Delimiter: ","
chr (5): country, purpose, mode, duration, age
dbl (4): year, visits_thousands, nights_thousands, expenditure_millions

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

international

usa <- international %>% 
  filter(country == "USA") %>% 
  mutate(year = as.character(year)) %>% 
  drop_na()

usa

usa %>% 
  ggplot(aes(x = visits_thousands,
             y = expenditure_millions)) +
  geom_point()

usa_scale <- usa %>%
  mutate(across(where(is_numeric), scale)) %>% 
  select(visits_thousands, expenditure_millions)

Warning: Problem while computing `..1 = across(where(is_numeric), scale)`.
ℹ Deprecated
Warning: Problem while computing `..1 = across(where(is_numeric), scale)`.
ℹ Deprecated
Warning: Problem while computing `..1 = across(where(is_numeric), scale)`.
ℹ Deprecated
Warning: Problem while computing `..1 = across(where(is_numeric), scale)`.
ℹ Deprecated
Warning: Problem while computing `..1 = across(where(is_numeric), scale)`.
ℹ Deprecated
Warning: Problem while computing `..1 = across(where(is_numeric), scale)`.
ℹ Deprecated
Warning: Problem while computing `..1 = across(where(is_numeric), scale)`.
ℹ Deprecated
Warning: Problem while computing `..1 = across(where(is_numeric), scale)`.
ℹ Deprecated
Warning: Problem while computing `..1 = across(where(is_numeric), scale)`.
ℹ Deprecated

head(usa_scale, 10)

usa_scale %>% 
  ggplot(aes(x = visits_thousands,
             y = expenditure_millions)) +
  geom_point()

library(broom)

max_k <- 20

k_clusters <- tibble(k = 1:max_k) %>% 
  mutate(
    kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25)),
    tidied = map(kclust, tidy),
    glanced = map(kclust, glance),
    augemnted = map(kclust, augment, usa)
  )

Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations
Warning: Problem while computing `kclust = map(k, ~kmeans(usa_scale, .x, nstart = 25))`.
ℹ did not converge in 10 iterations

k_clusters

augmented <- k_clusters %>% 
  unnest(augemnted)

augmented

augmented %>% 
  filter(k == 3) %>% 
  count(.cluster)

clusterings <- k_clusters %>% 
  unnest(glanced)

clusterings

ggplot(clusterings, aes(x=k, y=tot.withinss)) +
  geom_point() +
    geom_line() +
    scale_x_continuous(breaks = seq(1, 20, by = 1))

library(factoextra)

Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBa

fviz_nbclust(usa_scale, 
             kmeans, 
             method = "wss", 
             nstart = 25)

fviz_nbclust(usa_scale, 
             kmeans, 
             method = "silhouette", 
             nstart = 25)

Warning: did not converge in 10 iterations

fviz_nbclust(usa_scale, 
             kmeans, 
             method = "gap_stat", 
             nstart = 25, 
             k.max = 10)

Clustering k = 1,2,..., K.max (= 10): .. 

Warning: did not converge in 10 iterations

done
Bootstrapping, b = 1,2,..., B (= 100)  [one "." per sample]:
................

Warning: did not converge in 10 iterations

...............

Warning: Quick-TRANSfer stage steps exceeded maximum (= 180450)

...............

Warning: Quick-TRANSfer stage steps exceeded maximum (= 180450)

.... 50 

augmented <- augmented %>%
  filter(k == 3) %>% 
  mutate(cluster_group = case_when(
    .cluster == 3 ~ "smaller spenders",
    .cluster == 1 ~ "big spenders",
    .cluster == 2 ~ "medium spenders"
  )) %>% 
  select(-.cluster)

augmented %>% 
  filter(k == 3) %>% 
  ggplot(aes(x = visits_thousands,
             y = expenditure_millions))+
  geom_point(aes(colour = cluster_group))+
  facet_wrap(~ k) +
  labs(x = "\nVisits thousands",
       y = "Expenditure millions",
       title = "Expenditure vs Visits for Tourists from the USA",
       subtitle = "Years: 2002 - 2019\n") + 
  theme_minimal()

augmented %>% 
  filter(k == 3) %>% 
  filter(visits_thousands > 30)

augmented %>% 
  filter(k == 3) %>%
  count(cluster_group) %>% 
  ggplot(aes(x = cluster_group,
             y = n)) +
  geom_col()

augmented %>% 
  filter(k == 3) %>% 
  group_by(cluster_group) %>% 
  summarise(total_expenditure = sum(expenditure_millions)) %>% 
  ggplot(aes(x = cluster_group,
             y = total_expenditure)) +
  geom_col() 

augmented %>% 
  filter(k == 3) %>% 
  group_by(cluster_group) %>% 
  summarise(mean_expenditure = mean(expenditure_millions)) %>% 
  ggplot(aes(x = cluster_group,
             y = mean_expenditure)) +
  geom_col()

augmented %>% 
  filter(k == 3) %>% 
  group_by(cluster_group) %>% 
  summarise(total_visits = sum(visits_thousands)) %>% 
  ggplot(aes(x = cluster_group,
             y = total_visits)) +
  geom_col() 

augmented %>% 
  filter(k == 3) %>% 
  group_by(cluster_group, age) %>% 
  summarise(mean_expenditure = mean(expenditure_millions)) %>% 
  ggplot(aes(x = age,
             y = mean_expenditure)) +
  geom_col() +
  facet_wrap(~ cluster_group)

`summarise()` has grouped output by 'cluster_group'. You can override using the `.groups` argument.

augmented %>% 
  filter(k == 3) %>% 
  group_by(cluster_group, age) %>% 
  summarise(total_expenditure = sum(expenditure_millions)) %>% 
  ggplot(aes(x = age,
             y = total_expenditure)) +
  geom_col() +
  facet_wrap(~ cluster_group)

`summarise()` has grouped output by 'cluster_group'. You can override using the `.groups` argument.

augmented %>% 
  filter(k == 3) %>% 
  group_by(cluster_group, age) %>% 
  summarise(mean_visits = mean(visits_thousands)) %>% 
  ggplot(aes(x = age,
             y = mean_visits)) +
  geom_col() +
  facet_wrap(~ cluster_group)

`summarise()` has grouped output by 'cluster_group'. You can override using the `.groups` argument.

augmented %>% 
  filter(k == 3) %>% 
  group_by(cluster_group, age) %>% 
  summarise(total_visits = sum(visits_thousands)) %>% 
  ggplot(aes(x = age,
             y = total_visits)) +
  geom_col() +
  facet_wrap(~ cluster_group)

`summarise()` has grouped output by 'cluster_group'. You can override using the `.groups` argument.

augmented %>% 
  filter(k == 3) %>% 
  group_by(cluster_group, purpose) %>% 
  summarise(mean_expenditure = mean(expenditure_millions)) %>% 
  ggplot(aes(x = purpose,
             y = mean_expenditure)) +
  geom_col() +
  facet_wrap(~ cluster_group)

`summarise()` has grouped output by 'cluster_group'. You can override using the `.groups` argument.

augmented %>% 
  filter(k == 3) %>% 
  group_by(cluster_group, purpose) %>% 
  summarise(totql_expenditure = sum(expenditure_millions)) %>% 
  ggplot(aes(x = purpose,
             y = totql_expenditure)) +
  geom_col() +
  facet_wrap(~ cluster_group)

`summarise()` has grouped output by 'cluster_group'. You can override using the `.groups` argument.

augmented %>% 
  filter(k == 3) %>% 
  group_by(cluster_group, purpose) %>% 
  summarise(mean_visits = mean(visits_thousands)) %>% 
  ggplot(aes(x = purpose,
             y = mean_visits)) +
  geom_col() +
  facet_wrap(~ cluster_group)

`summarise()` has grouped output by 'cluster_group'. You can override using the `.groups` argument.

augmented %>% 
  filter(k == 3) %>% 
  group_by(cluster_group, purpose) %>% 
  summarise(total_visits = sum(visits_thousands)) %>% 
  ggplot(aes(x = purpose,
             y = total_visits)) +
  geom_col() +
  facet_wrap(~ cluster_group)

`summarise()` has grouped output by 'cluster_group'. You can override using the `.groups` argument.

augmented %>% 
  filter(k == 3) %>% 
  group_by(cluster_group, duration) %>% 
  count(duration) %>% 
  ggplot(aes(x = duration,
             y = n)) +
  geom_col() +
  facet_wrap(~ cluster_group)

augmented %>% 
  filter(k == 3) %>% 
  group_by(cluster_group, duration) %>% 
  summarise(totql_expenditure = sum(expenditure_millions)) %>% 
  ggplot(aes(x = duration,
             y = totql_expenditure)) +
  geom_col() +
  facet_wrap(~ cluster_group)

`summarise()` has grouped output by 'cluster_group'. You can override using the `.groups` argument.

augmented <- augmented %>%
  select(-c(k, kclust, tidied, glanced))

augmented

write_csv(augmented, "clean_data/usa.csv")